DensePose: Dense Human Pose Estimation In The Wild

Facebook AI Research group presented a paper on pose estimation. That will help Facebook with better understanding of the processed videos.

NEW: DensePose-COCO, a large-scale ground-truth dataset with image-to-surface correspondences manually annotated on 50K COCO images.

Project website: http://densepose.org/
Arxiv: https://arxiv.org/abs/1802.00434

#facebook #fair #cvpr #cv #CNN #dataset

Face recognition is now available as a JS-package with the help of face-api.js. It is built on top of #Tensorflow (js version).

https://itnext.io/face-api-js-javascript-api-for-face-recognition-in-the-browser-with-tensorflow-js-bcc2a6c4cf07?gi=a277ad002e2a

#cv #js #tf #dl #cnn

Faster R-CNN and Mask R-CNN in #PyTorch 1.0

Another release from #Facebook.

Mask R-CNN Benchmark: a fast and modular implementation for Faster R-CNN and Mask R-CNN written entirely in @PyTorch 1.0. It brings up to 30% speedup compared to mmdetection during training.

Webcam demo and ipynb file are available.

Github: https://github.com/facebookresearch/maskrcnn-benchmark

#CNN #CV #segmentation #detection

How Many Samples are Needed to Learn a Convolutional Neural Network

Article questioning fact that CNNs use a more compact representation than the Fully-connected Neural Network (FNN) and thus require fewer training samples to accurately estimate their parameters.

ArXiV: https://arxiv.org/abs/1805.07883

#CNN #nn

Deep learning cheatsheets, covering content of Stanford’s CS 230 class.

CNN: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-convolutional-neural-networks
RNN: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks
TipsAndTricks: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-deep-learning-tips-and-tricks

#cheatsheet #Stanford #dl #cnn #rnn #tipsntricks

Understanding Convolutional Neural Networks through Visualizations in PyTorch

Explanation of how #CNN works

Link: https://towardsdatascience.com/understanding-convolutional-neural-networks-through-visualizations-in-pytorch-b5444de08b91

#PyTorch #nn #DL

​​Object detection SOTA evolution over time.

#SOTA #CNN #objectdetection

"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet"

A "bag of words" of nets on tiny 17x17 patches suffice to reach AlexNet-level performance on ImageNet. A lot of the information is very local.

Paper: https://openreview.net/forum?id=SkfMWhAqYQ

#fun #CNN #CV #ImageNet

DGC-Net: Dense Geometric Correspondence network

Paper addresses the challenge of dense pixel correspondence estimation between two images. Practically, this means that it is about comparing different views of one object, which is very important to make #CV more robust.

ArXiV: https://arxiv.org/abs/1810.08393
Github: https://github.com/AaltoVision/DGC-Net
YouTube: https://www.youtube.com/watch?v=xnQMEr4FbHE
Project page: https://aaltovision.github.io/dgc-net-site/

#CNN #DL

How to hide from the AI surveillance state with a color printout

MIT’s team studied how to fool camera with and #adversarial print, exploiting the fact that #CNN can be tricked by adversarial examples into recognizing something wrong or not recongnizing image at all.

Link: https://www.technologyreview.com/f/613409/how-to-hide-from-the-ai-surveillance-state-with-a-color-printout/

#CV #DL #MIT

​​Using ‘radioactive data’ to detect if a data set was used for training

The authors have developed a new technique to mark the images in a data set so that researchers can determine whether a particular machine learning model has been trained using those images. This can help researchers and engineers to keep track of which data set was used to train a model so they can better understand how various data sets affect the performance of different neural networks.

The key points:
- the marks are harmless and have no impact on the classification accuracy of models, but are detectable with high confidence in a neural network;
- the image features are moved in a particular direction (the carrier) that has been sampled randomly and independently of the data
- after a model is trained on such data, its classifier will align with the direction of the carrier
- the method works in such a way that it is difficult to detect whether a data set is radioactive and to remove the marks from the trained model.

blogpost: https://ai.facebook.com/blog/using-radioactive-data-to-detect-if-a-data-set-was-used-for-training/
paper: https://arxiv.org/abs/2002.00937

#cv #cnn #datavalidation #image #data

​​Are Pre-trained Convolutions Better than Pre-trained Transformers?

In this paper, the authors from Google Research wanted to investigate whether CNN architectures can be competitive compared to transformers on NLP problems. It turns out that pre-trained CNN models outperform pre-trained Transformers on some tasks; they also train faster and scale better to longer sequences.

Overall, the findings outlined in this paper suggest that conflating pre-training and architectural advances is misguided and that both advances should be considered independently. The authors believe their research paves the way for a healthy amount of optimism in alternative architectures.

Paper: https://arxiv.org/abs/2105.03322

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-cnnbettertransformers

#nlp #deeplearning #cnn #transformer #pretraining

​​InceptionNeXt: When Inception Meets ConvNeXt

Large-kernel convolutions, such as those employed in ConvNeXt, can improve model performance but often come at the cost of efficiency due to high memory access costs. Although reducing kernel size may increase speed, it often leads to significant performance degradation.

To address this issue, the authors propose InceptionNeXt, which decomposes large-kernel depthwise convolution into four parallel branches along the channel dimension. This new Inception depthwise convolution results in networks with high throughputs and competitive performance. For example, InceptionNeXt-T achieves 1.6x higher training throughputs than ConvNeX-T and a 0.2% top-1 accuracy improvement on ImageNet-1K. InceptionNeXt has the potential to serve as an economical baseline for future architecture design, helping to reduce carbon footprint.

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-inceptionnext

Paper link:https://arxiv.org/abs/2303.16900

Code link: https://github.com/sail-sg/inceptionnext

#cnn #deeplearning #computervision